Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model

作     者：Marco Gotz Ferenc Leichsenring Thomas Kropp Peter Müller Tobias Falk Wolfgang Graf Michael Kaliske Welf-Guntram Drossel 

作者机构：Institute for Structural AnalysisTechnische UniversitatDresdenGermany Fraunhofer Institute for Machine Tools and Forming TechnologyDresdenGermany 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2018年第117卷第12期

页      面：387-423页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Deutsche Forschungsgemeinschaft  DFG  (GR 1504/9  KA 1163/34) 

主　　题：Design data mining computational intelligence meta-modelling permissible design space sensitivity analysis self-organizing maps inverse problem early stage of design clinching 

摘      要：Numerical mechanical models used for design of structures and processes are very complex and high-dimensionally *** understanding of the model characteristics is of interest for engineering tasks and subsequently for an efficient *** analysis methods are known and available to gain insight into existing *** this contribution,selected methods from various fields are applied to a real world mechanical engineering example of a currently developed clinching *** selection of introduced methods comprises techniques of machine learning and data mining,in which the utilization is aiming at a decreased numerical *** methods of choice are basically discussed and references are given as well as challenges in the context of meta-modelling and sensitivities are *** incremental knowledge gain is provided by a step-bystep application of the numerical methods,whereas resulting consequences for further applications are ***,a visualisation method aiming at an easy design guideline is *** visual decision maps incorporate the uncertainty coming from the reduction of dimensionality and can be applied in early stage of design.